Training update: 144,546/240,833 rows (60.02%) | +33 new @ 2025-11-01 01:03:34

README.md

@@ -25,7 +25,7 @@ pipeline_tag: fill-mask
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **59.82%** of planned data.
+- Status: **Early version** — trained on **60.02%** of planned data.
 
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
@@ -51,7 +51,7 @@ You can use this model to classify cybersecurity-related text — for example, w
 - Early classification of SIEM alert & events.
 
 ## 3. Bias, Risks, and Limitations 
-Because the model is based on a small subset (59.82%) of planned data, performance is preliminary and may degrade on unseen or specialized domains (industrial control, IoT logs, foreign language).
+Because the model is based on a small subset (60.02%) of planned data, performance is preliminary and may degrade on unseen or specialized domains (industrial control, IoT logs, foreign language).
 - Inherits any biases present in the base model (`boltuix/bert-micro`) and in the fine-tuning data — e.g., over-representation of certain threat types, vendor or tooling-specific vocabulary.
 - **Should not be used as sole authority for incident decisions; only as an aid to human analysts.**
 
@@ -75,9 +75,9 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 - **LR scheduler**: Linear with warmup
 
 ### Training Data
-- **Total database rows**: 240,825
-- **Rows processed (cumulative)**: 144,061 (59.82%)
-- **Training date**: 2025-11-01 00:02:32
+- **Total database rows**: 240,833
+- **Rows processed (cumulative)**: 144,546 (60.02%)
+- **Training date**: 2025-11-01 01:03:34
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012a13cdcb5e8ad58a741be28f70962ca7404b20a20d0697f46fecc44235466c
+oid sha256:99d960e6ef08e30c1d604d5afefddc64db18337c5c83034227048f90b46ed90f
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe407a128753518465be6a485ec504e1122d207c1100c36ee1b8d3bc7185d9e
+oid sha256:0ba800f39c0283ace72bb9786708cf784cac35bfda924ba98ff33d305d7546cc
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761955352.5820458,
-  "trained_at_readable": "2025-11-01 00:02:32",
-  "samples_this_session": 1603,
-  "new_rows_this_session": 486,
-  "trained_rows_total": 144061,
-  "total_db_rows": 240825,
-  "percentage": 59.81978615176996,
+  "trained_at": 1761959014.3563917,
+  "trained_at_readable": "2025-11-01 01:03:34",
+  "samples_this_session": 1616,
+  "new_rows_this_session": 33,
+  "trained_rows_total": 144546,
+  "total_db_rows": 240833,
+  "percentage": 60.0191834175549,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,